Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4952 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.8599. Min Act: -0.1700
Data Index: 4674060 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.7036. Min Act: -0.1700
Data Index: 3484437 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.7036. Min Act: -0.1700
Data Index: 291455 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.6724. Min Act: -0.1700
Data Index: 10101 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.6411. Min Act: -0.1700
Data Index: 3309785 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.5786. Min Act: -0.1700
Data Index: 2505995 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.5786. Min Act: -0.1700
Data Index: 8111168 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.4849. Min Act: -0.1700
Data Index: 5331155 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.4849. Min Act: -0.1700
Data Index: 5452163 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.4849. Min Act: -0.1700
Data Index: 3122575 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.4536. Min Act: -0.1700
Data Index: 2596872 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.4224. Min Act: -0.1700
Data Index: 5275207 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.4536. Min Act: -0.1700
Data Index: 3127172 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.4536. Min Act: -0.1700
Data Index: 1458332 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.3911. Min Act: -0.1700
Data Index: 6376773 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.3911. Min Act: -0.1700
Data Index: 6415859 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.3911. Min Act: -0.1700
Data Index: 6879760 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.3286. Min Act: -0.1700
Data Index: 5136986 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.3599. Min Act: -0.1700
Data Index: 449172 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8599. Min Range: -5.8599
Max Act: 5.3599. Min Act: -0.1700
Data Index: 1754183 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19